CN110232976A - A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric - Google Patents
A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric Download PDFInfo
- Publication number
- CN110232976A CN110232976A CN201910585638.9A CN201910585638A CN110232976A CN 110232976 A CN110232976 A CN 110232976A CN 201910585638 A CN201910585638 A CN 201910585638A CN 110232976 A CN110232976 A CN 110232976A
- Authority
- CN
- China
- Prior art keywords
- measurement
- curve
- signal
- muscle
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Heart & Thoracic Surgery (AREA)
- Theoretical Computer Science (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Animal Behavior & Ethology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric, this method is that motion process is divided into the period, identification code is set within the period, judging whether to meet movement described in pre-programmed curve for identification code and preset value comparison, to realize signal identification, which is realized using more Physiological Signal Acquiring Systems；The recognition methods is under the premise of the degree of freedom of motion is limited, the behavior that motion capture just identifies people can not be had to, subjective attention and operation are not needed, delay is not grown, and is not taken up space, it can be achieved that monitoring to tendency of having an effect, it frequently drives in, mutual-action behavior not bery high to reliability requirement, the fields such as entertainment interactive, publilc health monitoring provide signal output, it has a extensive future, more than identifies movement, the mode of having an effect of lesion person can also change；This method can be used for monitoring human lesion, assessment Labor Risk, have considerable practical value and economic potential.
Description
Technical field
The present invention relates to the fields that ergonomics and signal acquisition intersect, especially a kind of to be based on waist shoulder surface myoelectric
The Activity recognition method of measurement.
Background technique
Measurement to muscle electricity is to monitor the important means of human body signal, more reliable in laboratory environments, is answered extensively
For medical treatment, ergonomics research etc., muscle electric wave amplitude and frequency are detected by myoelectric sensor.Research for myoelectricity
Quite mature, but myoelectricity signal identification poor reliability itself, difference is very big between different objects, to the software of muscle and joint load
Simulation is mainly based upon the calculating of reverse dynamic (dynamical) muscles and bones dummy, and it is more accurate to calculate greatly and when overloaded in movement range, but
Effective identification of having an effect inside is difficult to when acting unobvious.
There are many shortcomings for current electromyography signal identification: the electrometric preparation of flesh needs step more, muscle
Mechanism of having an effect is complicated, and personal measurement may relate to ethics problem, the signal wave amplitude stability measured is poor, vulnerable to electrocardio and
The flexible interference of the fat (ECG) and skin of body surface, the precedent for applying to control system are less；It is not easy to apply to want reliability
Ask high automation field and labour operating condition and Entertainment Scene, the research controlled for EMG feedback signal main
Prosthesis control and human body slave side are concentrated on, this kind of scene man-machine interface is stablized in small part, and acquisition difficulty is small, rarely has
Equipment is controlled using the identification to the small of the back muscle signal, is mainly the absence of suitable and big commercial value research scene.
It is limited to trick mouth in terms of the limbs signal fan-out capability of people, often enables the interaction capability of spectators and efficiency limited
System cannot freely switch according to outdoor scene demand and interactive demand；Human-computer interaction needs the time of human body consciousness and output control, meeting
Reduce human-computer interaction efficiency；People needs to pay attention to power using hand mouth foot output signal, influences to think deeply, and cannot be helped using instinct
Help control；It is realized and is controlled using subjective consciousness, the brain load that will lead to operation interaction is big, causes anxiety easily tired, comfort level is not
Foot, thus need to redesign a kind of electrometric Activity recognition method of flesh.
The present invention be exactly in order to solve problem above and carry out improvement.
Summary of the invention
The technical problem to be solved by the invention is to provide a kind of acquisition mode to environment with pay attention to force request it is low, versatility
More preferably, good compatibility, the Activity recognition method based on the measurement of waist shoulder surface myoelectric of high reliablity.
The present invention is that technical solution used by solving its technical problem is:
A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric, this method is that motion process is divided into the time
Section, is arranged identification code within the period, judges whether to meet movement described in pre-programmed curve for identification code and preset value comparison
To realize signal identification, which is realized using more Physiological Signal Acquiring Systems, and Physiological Signal Acquiring System includes
Cortex synchronous platform, input terminal include motion capture system and myoelectricity acquisition system, and the signal of input respectively completes modulus
After conversion, number is realized in the synchronous and preliminary data processing of Cortex software desk Implementation, then by adapter and amplifier
Word signal output, into identification and compiling link, implementation step are as follows:
S1, preparation, motion capture and myoelectricity measurement synchronism output are as a result, draw standard curve of the muscle in regulation movement
With the muscles and bones dummy of reflection real-time status, it is smoothed using output result of the Cortex synchronous platform to motion capture；
S2, measurement complete the measurement of spontaneous contractions, acquire standard muscle curve signal, form pre-programmed curve, establish task
Database；
S3, differentiate process, by being compared with pre-programmed curve, carry out correlation analysis differentiate whether deliberate action；
S4, recognition result realize signal identification by step S3；
The step S3 can synchronize addition sensor signal, it is described in step s 2, extraction standard muscle curve signal group
At identification code；
Further, in step sl, the electromyography signal obtained under scene on the spot will be compared with standard curve, utilize SPSS
(V19) Spearman correlation analysis is carried out, such as finds most of rank correlation of 16 time steps, then it is assumed that meet identification item
Part, then system can recognize corresponding actions, such as uncorrelated, then judges whether that there is a situation where antagonism power to increase severely, when necessary using poly-
Alanysis is clustered to the main muscle group of waist curve of having an effect.The main muscle group Clustering result of waist, waist and shoulder master
Muscle group is wanted to have an effect curve by derived indice group result, all as identification independent variable；
Specifically, the smoothing processing includes the denoising of the output result progress to motion capture, goes clutter and removal
The processing of envelope jump point；
Wherein, the muscles and bones dummy is automatically generated by KineAnalyser software according to the reflective locus of points.
Working principle are as follows: be directed to human body main actions, while extracting many places muscle signal, form specific identification code, identification
Code is compared with predetermined value, is identified according to threshold value and preset logic.
The present invention has the advantages that the recognition methods can not have to motion capture under the premise of the degree of freedom of motion is limited
The behavior for just identifying people, do not need it is subjective pay attention to and operation, delay are not grown, do not take up space, it can be achieved that prison to tendency of having an effect
It surveys, frequently drives in, mutual-action behavior not bery high to reliability requirement, the fields offer letter such as entertainment interactive, publilc health monitoring
Number output, have a extensive future, more than identify movement, the mode of having an effect of lesion person can also change；This method can be used for supervising
Human lesion, assessment Labor Risk are surveyed, there is considerable practical value and economic potential.
Detailed description of the invention
Fig. 1 is that motion process divides in a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric proposed by the present invention
For the curve graph of period.
Fig. 2 is that Lon-R-E is right in a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric proposed by the present invention
The curve graph of longissimus measured value and the right iliocostalis measured value of Ilio-R-E.
Fig. 3 is that waist muscle is being put in a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric proposed by the present invention
Loose single bend in percentage curve figure of having an effect.
Specific embodiment
In order to be easy to understand the technical means, the creative features, the aims and the efficiencies achieved by the present invention, tie below
Diagram and specific embodiment are closed, the present invention is further explained.
Referring to figs. 1 to shown in Fig. 3, must should be acquired simultaneously based on the Activity recognition method that waist shoulder surface myoelectric measures multiple
Waist shoulder human muscle's electric signal, sometimes in combination with the anthropoid angle transducer of gyroscope, entire motion process according to height of C.G.
Track or particular body portion action trail are divided into some time, and measurement muscle is had an effect curve, gather to this curve
Class extracts one group of muscle and has an effect the derivative of wave envelope, as identification code, continuous multistage identification code in the section of each class
It is compared with preset value, if it find that correlation is high, then meets the described movement of pre-programmed curve, realize signal identification；
This method utilizes Cortex and Kinanalyser system, the myoelectricity data and curves of acquisition process specific action, with tool
After the default change curve of body muscle carries out rank correlation comparison, judgement, waveform arranges, wave band is chosen, control is realized in amplification output
System.Using the liveness signal curve of muscle of trunk, to control people, handle, environment, with identification bend over-stretch out one's hand and operate-straighten one's back
For this process, implementation step are as follows:
S1, preparation include Cortex synchronous platform using more Physiological Signal Acquiring Systems, and input terminal includes motion capture
System and myoelectricity acquisition system, after the signal of input respectively completes analog-to-digital conversion, Cortex software desk Implementation it is synchronous and
Preliminary data processing, then digital signal output is realized by adapter and amplifier, into identification and compiling link；
Motion capture and myoelectricity measurement synchronism output are as a result, standard curve and reflection of the drafting muscle in regulation movement are real
When state muscles and bones dummy；
The electromyography signal obtained under scene on the spot will be compared with standard curve, carry out Spearman using SPSS (V19)
Correlation analysis such as finds most of rank correlation of 16 time steps, then it is assumed that meets identification condition, then system can recognize phase
It should act；
It is such as uncorrelated, then judge whether that there is a situation where antagonism power to increase severely, it is main to waist using clustering when necessary
Muscle group curve of having an effect is clustered.The main muscle group Clustering result of waist, waist and the main muscle group of shoulder have an effect curve by
Derived indice group result, all as identification independent variable.
S2, measurement realize the foundation of discrimination standard, acquire standard muscle curve signal, form pre-programmed curve, establish task
Database；
S3, differentiate process, by being compared with pre-programmed curve, carry out correlation analysis differentiate whether deliberate action；
S4, recognition result realize signal identification by step S3；
The step S3 can synchronize addition sensor signal, it is described in step s 2, extraction standard muscle curve signal group
At identification code；
Further, in step sl, the electromyography signal obtained under scene on the spot will be compared with standard curve, utilize SPSS
(V19) Spearman correlation analysis is carried out, such as finds most of rank correlation of 16 time steps, then it is assumed that meet identification item
Part, then system can recognize corresponding actions, such as uncorrelated, then judges whether that there is a situation where antagonism power to increase severely, when necessary using poly-
Alanysis is clustered to the main muscle group of waist curve of having an effect.The main muscle group Clustering result of waist, waist and shoulder master
Muscle group is wanted to have an effect curve by derived indice group result, all as identification independent variable；
Specifically, the smoothing processing includes the denoising of the output result progress to motion capture, goes clutter and removal
The processing of envelope jump point；
Wherein, the muscles and bones dummy is automatically generated by KineAnalyser software according to the reflective locus of points, and nearside closes between referring to
The short transverse motion profile form for saving (PIP) and center of gravity is such as schemed, the preparatory division to waveform.Every time from body setting in motion,
To slowing down close to target, the positive and negative inflection point of trunk acceleration is recorded by motion capture system, and position of human center variation is anti-
Good repeatability is mirrored, each circulation is touched target 3 times, passes through 6 rate curve inflection points every time, minimum by 1 center of gravity
The surface myoelectric data and curves of each duty cycle are divided into 8 steps by point plus 6 rate curve inflection points.Then by 8 steps
All it is uniformly divided into 2 parts.The longissimus myoelectricity curve of every circulation is divided into 16 sections according to this time-sharing method.Accordingly
The curved journey that extends through of the dynamic of manikin is also reduced to 16 sections, as shown in Figure 1, every section is known as 1 time step, the height of center of gravity
Degree-time graph is as the curve for dividing time step.
In step s 2, it bends over to stretch in singlehanded task, the major muscles of selection include longissimus, iliocostalis and deltoid muscle,
Function is that two sides are straightened one's back, lifted on body rotation and single armed respectively.
Each experimenter prostrate before operation experiments, upper body stretching are suspended from outside bed, and the lower part of the body is fixed, and upper body is by auxiliary from side
Edge direction is controlled downwards, and experimenter's back is had an effect backward as possible, before every secondary control is realized, needs first to complete maximum spontaneous contractions
(MVC) measuring process is had an effect 10 seconds after hearing prompt tone, selects RMS value maximum continuous 3 seconds, calculates mean value in 3 seconds of RMS.It is whole
A process is spaced to calculate MVC mean value afterwards in triplicate.
Before analog to digital (A/D) conversion, digital full-wave rectification SEMG signal is limited in 30 to 500 hertz of (band logicals
Filter).
It 16 periods to the standardization electromyography signal for being tested muscle (totally 5) each of in a cycle, utilizes
Spss (V19) software is classified, and Euclidean distance between scatterplot is calculated, and 16 segment datas of waist muscle curve are clustered, are divided into
5-7 group.Trapezius muscle curve part office class is directly differentiated using each section of curve derivative direction.
In the measurement of many experiments room, if some tested muscle curve is all consistent in the result of some time step,
It is included in affiliated class, if opposite consistency is bad, is classified as " uncertain ", which can not identify.
Uncertainty, which includes: operation by human hand, interrupts effect to what waist loosened effect；Subjective desire can bring antagonism
Effect, such as the subjective precise manipulation that carry out trunk balance adjustment or equilibrium,transient sense missing and hand, all may
Opposing muscle is caused to be had an effect sharp increase, the result of time step is uncertain where causing.
It identifies lower totally 8 groups of waist process signal, is composed of three classes identification variable.4th, 5,6 group of signal includes uncertain
Vector, confirmation message needs to acquire other classification synchronization signals, such as hand trigger switch or space angle transducer, then pole
Big to reduce erroneous judgement possibility occurrence, signal identification logical design is as shown in table 1, with the asymmetric of one group of young man in table 1, stretches the right side
For the task that hand is bent over simultaneously, a standard curve is established, curve is classified as 5 groups.
The Clustering and identification signal that table 1 is asymmetric when bending over
For above procedure for acquiring standard muscle curve signal, this only identifies the premise of specific action, if not how many
Class acts it is necessary to repeat the above experiment how many times, and establishes corresponding task database.
In step s3, it needs to limit body freedom degree to a certain extent first, otherwise four limbs and any type driven are inclined
It is inaccurate all to may cause identification from preset standard.Need to dress in advance the left longissimus electrode tip of (1) right trapezius muscle electrode tip (2),
(3) right longissimus electrode tip, (4) right iliocostalis electromyographic signal acquisition device, (5) left iliocostalis electromyographic signal acquisition device.Nearby need
There is electromyography signal antenna.As can the synchronous angle transducer that is added will increase accuracy of identification.
The intention of user is different, arm action is different, whether has pause or precise manipulation all can cause the very big of signal
Variation, therefore more signal path apparatus measures, just have accurate differentiation, channel here refers not only to myoelectricity, is sensor
Equal signals can also synchronize addition.
Waist curve of having an effect is very sensitive with job change, if the poke one's head in figure loosened is such as without hand activities
Shown in Fig. 3.
After signal synchronizes, it is transferred to the information processing terminal.Using the rank correlation for 16 periods for surveying 5 curves,
Compared with by test obtained pre-programmed curve before, progress correlation analysis, if significantly property coefficient less than 0.05, and phase relation
Number is greater than 0.5, then differentiates that movement is deliberate action, otherwise further differentiates in each phylogenetic group whether related, such as discriminating step
In 4-8, curve whether to it is default related, as still uncorrelated, differentiate it is not deliberate action；Rank correlation in such as each main group, then sentence
It is not deliberate action.
This method has a characteristic that
1) acquisition mode is low with force request is paid attention to environment, and versatility is more preferable.
Electromyography signal has the characteristics that in time and sensitive, can have an effect from subjective driving, can also be from subconsciousness
And natural reaction, low to absorbed force request, reaction in time, convenient for application, can be used for the auxiliary of mental ability weak person.It is not take up hand
The primary sensing organs such as eye ear, increase human body operational capacity, with original operation good compatibility, do not interfere, do not need vulnerable to acousto-optic
Larger space.It is continuous for exporting muscle liveness curve, it may be achieved soft delicate man-machine mechanics interaction.It can be achieved to use trunk
The adjacent parts such as thigh are controlled, can be used for the infull person's auxiliary of limbs and pathological research.
2) good compatibility, high reliablity
The human muscle's signal mainly acquired includes: the surface portion (waist of two sides longissimus of the erector spinae group at back
Position and iliocostalis) and shoulders trapezius muscle, be easier to acquire, be disturbed few, do not influence privacy places, Behavior law is multiple
Miscellaneous and not easily pass through external movement judgement, traditional approach is easy to by subjective reason and interference and wave the measurement at single position
It is dynamic, but this method is utilized, the relative value of the signal combination at 5 positions is monitored, identification certainty is relatively high.
The mode of this packet segmentation is not standardized (to be converted to by identification waveform or namely muscle and have an effect hundred
Point ratio) root mean square (RMS) identify size of having an effect, it is insensitive to signal absolute value, but to envelope of curve line it is opposite walking
Gesture is sensitive, solves the problems, such as that electromyography signal absolute value difference is big, needs to survey muscle maximum independently before also solving experiment every time
The problem of shrinking (MVC).Because only seeing rank correlation, also there is no need to be standardized into percentage.
In measurement process, electrode tip, which falls off, does not need to repeat MVC step yet, and only need to clear up body surface pastes telegram in reply cartridge again,
Duplicate measurements, this is the considerable advantage that this method is differentiated by rank correlation measurement, greatly simplifies process, improves general
Property, it reduces using difficulty.
The signal recognition method is differentiated respectively with the rank correlation of its pre-programmed curve based on each muscle myoelectricity curve, is passed through
The form trend for checking each curve, it is insensitive to absolute value even its amplitude quantity, after solving each patch of myoelectricity measurement
The biggish problem of absolute value difference, the patch that also solves the problems, such as to fall off every time will reform MVC step, the step for need
It wants professional to assist and subject is needed to have an effect with all strength, may cause injury.Only body surface need to be cleared up pastes telegram in reply cartridge again, weight
Repetition measurement amount greatly simplifies process, improves versatility；Selectively replaced using the variation of one group of muscle and body angle
Whole motion profile and myoelectricity monitoring device, can be to avoid dedicated place and large scale equipment is used the problem of, without doing three
Preset step in place needed for capturing；In such a way that segmentation and cluster combine, jitter can be likely to occur to precognition
Position (such as in Fig. 2 step 9) carry out selectivity ignore, to stablize obviously be not easily susceptible to interference section be compared, improve
Collection accuracy；Selectivity is acquired part muscle and activity, reduces equipment and place, and sport technique segment is few, adapts to
More application scenarios；Even if acquisition signal path is also the amount doesn't matter to individual task, angle transducer and soft-touch control can be added,
The reliability standard of system can be selected as needed.
The basic principles, main features and advantages of the present invention have been shown and described above.The technology of the industry
Personnel are it should be appreciated that the present invention is not limited to the above embodiments, and the above embodiments and description only describe this
The principle of invention, various changes and improvements may be made to the invention without departing from the spirit and scope of the present invention, these changes
Change and improvement all fall within the protetion scope of the claimed invention.The claimed scope of the invention by appended claims and its
Equivalent defines.
Claims (4)
1. a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric, this method is that motion process is divided into the period,
Identification code is set within the period, identification code and preset value comparison are judged whether to meet movement described in pre-programmed curve with reality
Existing signal identification, it is characterised in that:
The recognition methods realizes that Physiological Signal Acquiring System synchronizes flat comprising Cortex using more Physiological Signal Acquiring Systems
Platform, input terminal include motion capture system and myoelectricity acquisition system, implementation step are as follows:
S1, preparation, motion capture and myoelectricity measurement synchronism output as a result, draw muscle regulation movement in standard curve and instead
The muscles and bones dummy for reflecting real-time status is smoothed using output result of the Cortex synchronous platform to motion capture；
S2, measurement complete the measurement of spontaneous contractions, acquire standard muscle curve signal, form pre-programmed curve, establish task data
Library；
S3, differentiate process, by being compared with pre-programmed curve, carry out correlation analysis differentiate whether deliberate action；
S4, recognition result realize signal identification by step S3；
The step S3 can synchronize addition sensor signal, it is described in step s 2, extraction standard muscle curve signal composition is known
Other code.
2. a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric as described in claim 1, which is characterized in that in step
In rapid S1, the electromyography signal obtained under scene on the spot will be compared with standard curve, and it is related to carry out Spearman using SPSS (V19)
Property analysis.
3. a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric as described in claim 1, which is characterized in that described
Smoothing processing includes the denoising of the output result progress to motion capture, removes clutter and remove the processing of envelope jump point.
4. a kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric as described in claim 1, which is characterized in that described
Muscles and bones dummy is automatically generated by KineAnalyser software according to the reflective locus of points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585638.9A CN110232976B (en) | 2019-07-01 | 2019-07-01 | Behavior identification method based on waist and shoulder surface myoelectricity measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910585638.9A CN110232976B (en) | 2019-07-01 | 2019-07-01 | Behavior identification method based on waist and shoulder surface myoelectricity measurement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110232976A true CN110232976A (en) | 2019-09-13 |
| CN110232976B CN110232976B (en) | 2023-05-02 |
Family
ID=67857489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910585638.9A Active CN110232976B (en) | 2019-07-01 | 2019-07-01 | Behavior identification method based on waist and shoulder surface myoelectricity measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110232976B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110859620A (en) * | 2019-11-19 | 2020-03-06 | 上海电机学院 | Unidirectional video signal-based lumbar spinal erector muscle activity identification and prediction method |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103417218A (en) * | 2013-08-27 | 2013-12-04 | 中山大学附属第一医院 | Parameter acquisition evaluating system and method of upper limb movement |
| CN104107134A (en) * | 2013-12-10 | 2014-10-22 | 中山大学 | Myoelectricity feedback based upper limb training method and system |
| CN106295212A (en) * | 2016-08-18 | 2017-01-04 | 电子科技大学 | A kind of electromyographic signal synchronization processing method based on polynary empirical mode decomposition |
| CN106333688A (en) * | 2016-09-21 | 2017-01-18 | 北京机械设备研究所 | Real-time identification method for ankle joint movement |
| CN106388812A (en) * | 2016-09-21 | 2017-02-15 | 广州视源电子科技股份有限公司 | A marking method and system for the data types of electroencephalogram signals in a waking state |
| CN106420124A (en) * | 2016-10-10 | 2017-02-22 | 上海电机学院 | Method for myoelectrically controlling artificial hand simulation system of virtual robot |
| CN106781283A (en) * | 2016-12-29 | 2017-05-31 | 东北大学秦皇岛分校 | A kind of method for detecting fatigue driving based on soft set |
| CN107357419A (en) * | 2017-06-13 | 2017-11-17 | 中国科学院深圳先进技术研究院 | A kind of motion recognition system and method based on co-contraction rate |
| CN108209911A (en) * | 2017-05-25 | 2018-06-29 | 深圳市前海未来无限投资管理有限公司 | A kind of electromyographic signal collection method and device |
| CN108814597A (en) * | 2018-04-16 | 2018-11-16 | 龚映清 | A kind of rehabilitation training evaluating method interacted based on motion information with myoelectricity and system |
| CN108888265A (en) * | 2018-05-23 | 2018-11-27 | 四川斐讯信息技术有限公司 | A kind of movement method for early warning and device |
| CN109222969A (en) * | 2018-10-31 | 2019-01-18 | 郑州大学 | A kind of wearable human upper limb muscular movement fatigue detecting and training system based on Fusion |
| CN109567798A (en) * | 2018-12-26 | 2019-04-05 | 杭州电子科技大学 | Daily behavior recognition methods based on myoelectricity small echo coherence and support vector machines |
| CN109716443A (en) * | 2016-07-12 | 2019-05-03 | Hhs株式会社 | Utilize the exercise management method and system of electromyography transducer |
-
2019
- 2019-07-01 CN CN201910585638.9A patent/CN110232976B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103417218A (en) * | 2013-08-27 | 2013-12-04 | 中山大学附属第一医院 | Parameter acquisition evaluating system and method of upper limb movement |
| CN104107134A (en) * | 2013-12-10 | 2014-10-22 | 中山大学 | Myoelectricity feedback based upper limb training method and system |
| CN109716443A (en) * | 2016-07-12 | 2019-05-03 | Hhs株式会社 | Utilize the exercise management method and system of electromyography transducer |
| CN106295212A (en) * | 2016-08-18 | 2017-01-04 | 电子科技大学 | A kind of electromyographic signal synchronization processing method based on polynary empirical mode decomposition |
| CN106333688A (en) * | 2016-09-21 | 2017-01-18 | 北京机械设备研究所 | Real-time identification method for ankle joint movement |
| CN106388812A (en) * | 2016-09-21 | 2017-02-15 | 广州视源电子科技股份有限公司 | A marking method and system for the data types of electroencephalogram signals in a waking state |
| CN106420124A (en) * | 2016-10-10 | 2017-02-22 | 上海电机学院 | Method for myoelectrically controlling artificial hand simulation system of virtual robot |
| CN106781283A (en) * | 2016-12-29 | 2017-05-31 | 东北大学秦皇岛分校 | A kind of method for detecting fatigue driving based on soft set |
| CN108209911A (en) * | 2017-05-25 | 2018-06-29 | 深圳市前海未来无限投资管理有限公司 | A kind of electromyographic signal collection method and device |
| CN107357419A (en) * | 2017-06-13 | 2017-11-17 | 中国科学院深圳先进技术研究院 | A kind of motion recognition system and method based on co-contraction rate |
| CN108814597A (en) * | 2018-04-16 | 2018-11-16 | 龚映清 | A kind of rehabilitation training evaluating method interacted based on motion information with myoelectricity and system |
| CN108888265A (en) * | 2018-05-23 | 2018-11-27 | 四川斐讯信息技术有限公司 | A kind of movement method for early warning and device |
| CN109222969A (en) * | 2018-10-31 | 2019-01-18 | 郑州大学 | A kind of wearable human upper limb muscular movement fatigue detecting and training system based on Fusion |
| CN109567798A (en) * | 2018-12-26 | 2019-04-05 | 杭州电子科技大学 | Daily behavior recognition methods based on myoelectricity small echo coherence and support vector machines |
Non-Patent Citations (2)
| Title |
|---|
| 肖凯: "基于表面肌电信号的人体动作识别算法研究进展", 《生物信息学》 * |
| 赵新刚: "基于表面肌电信号的人体运动意图识别方法研究", 《仪器仪表学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110859620A (en) * | 2019-11-19 | 2020-03-06 | 上海电机学院 | Unidirectional video signal-based lumbar spinal erector muscle activity identification and prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110232976B (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104107134B (en) | Upper limbs training method and system based on EMG feedback | |
| CN108829245B (en) | A kind of virtual sand table intersection control routine based on multi-modal brain-machine interaction technology | |
| Cheng et al. | Active capacitive sensing: Exploring a new wearable sensing modality for activity recognition | |
| JP6178838B2 (en) | System for acquiring and analyzing muscle activity and method of operation thereof | |
| US20200260962A1 (en) | System and methods for acquisition and analysis of health data | |
| CN103997955B (en) | The method of the atrial fibrillation in detection electrocardiogram | |
| Hou et al. | A real-time QRS detection method based on phase portraits and box-scoring calculation | |
| US20170143226A1 (en) | Action Recognition Method and Device Based on Surface Electromyography Signal | |
| CN105181998B (en) | A method of the SEMG and movement locus of arm when detection shooting | |
| CN103699226A (en) | Tri-modal serial brain-computer interface method based on multi-information fusion | |
| CN103699217A (en) | Two-dimensional cursor motion control system and method based on motor imagery and steady-state visual evoked potential | |
| CN103126655A (en) | Non-binding goal non-contact pulse wave acquisition system and sampling method | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| Liu et al. | How Long Are Various Types of Daily Activities? Statistical Analysis of a Multimodal Wearable Sensor-based Human Activity Dataset. | |
| CN109199417A (en) | A kind of augmented reality method and system for athletic rehabilitation treatment | |
| CN113160921A (en) | Construction method and application of digital human cardiovascular system based on hemodynamics | |
| CN108968989A (en) | One kind based on it is psychologic stress training system and its application method | |
| CN114298089A (en) | Multi-mode strength training assisting method and system | |
| CN112603319A (en) | High-fear psychological monitoring and evaluating system based on virtual reality technology | |
| WO2022193851A1 (en) | Method and system for recognizing user actions | |
| Andrade et al. | On the relationship between features extracted from EMG and force for constant and dynamic protocols | |
| CN110232976A (en) | A kind of Activity recognition method based on the measurement of waist shoulder surface myoelectric | |
| Mekruksavanich et al. | Badminton activity recognition and player assessment based on motion signals using deep residual network | |
| Zhang et al. | Activity recognition of the torso based on surface electromyography for exoskeleton control | |
| CN109820523A (en) | Psychological tester control method, device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |